| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 282, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.10638297872340426, |
| "grad_norm": 2.73763108253479, |
| "learning_rate": 4.840425531914894e-05, |
| "loss": 7.0593, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2127659574468085, |
| "grad_norm": 4.184208869934082, |
| "learning_rate": 4.663120567375887e-05, |
| "loss": 4.3509, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3191489361702128, |
| "grad_norm": 2.815650224685669, |
| "learning_rate": 4.48581560283688e-05, |
| "loss": 2.3531, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.425531914893617, |
| "grad_norm": 1.4433400630950928, |
| "learning_rate": 4.3085106382978725e-05, |
| "loss": 1.3585, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5319148936170213, |
| "grad_norm": 1.3113492727279663, |
| "learning_rate": 4.1312056737588654e-05, |
| "loss": 0.8143, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6382978723404256, |
| "grad_norm": 1.1828652620315552, |
| "learning_rate": 3.953900709219858e-05, |
| "loss": 0.7293, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7446808510638298, |
| "grad_norm": 1.0307129621505737, |
| "learning_rate": 3.776595744680852e-05, |
| "loss": 0.5471, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.851063829787234, |
| "grad_norm": 0.7392168045043945, |
| "learning_rate": 3.599290780141844e-05, |
| "loss": 0.5001, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.9574468085106383, |
| "grad_norm": 1.0385117530822754, |
| "learning_rate": 3.4219858156028374e-05, |
| "loss": 0.4176, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0638297872340425, |
| "grad_norm": 0.8549280166625977, |
| "learning_rate": 3.2446808510638296e-05, |
| "loss": 0.4753, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.1702127659574468, |
| "grad_norm": 0.6353434920310974, |
| "learning_rate": 3.067375886524823e-05, |
| "loss": 0.3597, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.2765957446808511, |
| "grad_norm": 0.5479038953781128, |
| "learning_rate": 2.8900709219858156e-05, |
| "loss": 0.332, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.3829787234042552, |
| "grad_norm": 0.7110474705696106, |
| "learning_rate": 2.7127659574468084e-05, |
| "loss": 0.4116, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.4893617021276595, |
| "grad_norm": 0.7794738411903381, |
| "learning_rate": 2.5354609929078016e-05, |
| "loss": 0.3355, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.5957446808510638, |
| "grad_norm": 0.5863938927650452, |
| "learning_rate": 2.3581560283687945e-05, |
| "loss": 0.3371, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.702127659574468, |
| "grad_norm": 1.5034053325653076, |
| "learning_rate": 2.1808510638297873e-05, |
| "loss": 0.4327, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.8085106382978724, |
| "grad_norm": 0.534168541431427, |
| "learning_rate": 2.0035460992907805e-05, |
| "loss": 0.3472, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.9148936170212765, |
| "grad_norm": 0.5549598336219788, |
| "learning_rate": 1.8262411347517733e-05, |
| "loss": 0.3687, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.021276595744681, |
| "grad_norm": 0.5196494460105896, |
| "learning_rate": 1.6489361702127658e-05, |
| "loss": 0.2445, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.127659574468085, |
| "grad_norm": 0.5457848310470581, |
| "learning_rate": 1.4716312056737588e-05, |
| "loss": 0.2548, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.2340425531914896, |
| "grad_norm": 0.5511345863342285, |
| "learning_rate": 1.2943262411347517e-05, |
| "loss": 0.3374, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.3404255319148937, |
| "grad_norm": 0.4927542805671692, |
| "learning_rate": 1.1170212765957447e-05, |
| "loss": 0.3462, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.4468085106382977, |
| "grad_norm": 0.5920850038528442, |
| "learning_rate": 9.397163120567375e-06, |
| "loss": 0.2803, |
| "step": 230 |
| }, |
| { |
| "epoch": 2.5531914893617023, |
| "grad_norm": 0.5556482076644897, |
| "learning_rate": 7.6241134751773054e-06, |
| "loss": 0.3066, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.6595744680851063, |
| "grad_norm": 0.4986216723918915, |
| "learning_rate": 5.851063829787235e-06, |
| "loss": 0.3169, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.7659574468085104, |
| "grad_norm": 0.7671786546707153, |
| "learning_rate": 4.078014184397164e-06, |
| "loss": 0.307, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.872340425531915, |
| "grad_norm": 0.8555495142936707, |
| "learning_rate": 2.304964539007092e-06, |
| "loss": 0.2727, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.978723404255319, |
| "grad_norm": 0.5921739935874939, |
| "learning_rate": 5.319148936170213e-07, |
| "loss": 0.3595, |
| "step": 280 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 282, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 585555443712000.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
